Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313016741> ?p ?o ?g. }
- W4313016741 abstract "This paper addresses the problem of learning control policies for mobile robots, modeled as unknown Markov Decision Processes (MDPs), that are tasked with temporal logic missions, such as sequencing, coverage, or surveillance. The MDP captures uncertainty in the workspace structure and the outcomes of control decisions. The control objective is to synthesize a control policy that maximizes the probability of accomplishing a high-level task, specified as a Linear Temporal Logic (LTL) formula. To address this problem, we propose a novel accelerated model-based reinforcement learning (RL) algorithm for LTL control objectives that is capable of learning control policies significantly faster than related approaches. Its sample-efficiency relies on biasing exploration towards directions that may contribute to task satisfaction. This is accomplished by leveraging an automaton representation of the LTL task as well as a continuously learned MDP model. Finally, we provide comparative experiments that demonstrate the sample efficiency of the proposed method against recent RL methods for LTL objectives." @default.
- W4313016741 created "2023-01-05" @default.
- W4313016741 creator A5014874021 @default.
- W4313016741 date "2022-10-23" @default.
- W4313016741 modified "2023-10-16" @default.
- W4313016741 title "Accelerated Reinforcement Learning for Temporal Logic Control Objectives" @default.
- W4313016741 cites W1491843047 @default.
- W4313016741 cites W1989315746 @default.
- W4313016741 cites W2107726111 @default.
- W4313016741 cites W2124623089 @default.
- W4313016741 cites W2168405694 @default.
- W4313016741 cites W2226453522 @default.
- W4313016741 cites W2554009248 @default.
- W4313016741 cites W2736666525 @default.
- W4313016741 cites W2931553127 @default.
- W4313016741 cites W2953302092 @default.
- W4313016741 cites W3011250830 @default.
- W4313016741 cites W3021964239 @default.
- W4313016741 cites W3026873144 @default.
- W4313016741 cites W3090827750 @default.
- W4313016741 cites W3092156990 @default.
- W4313016741 cites W3176904019 @default.
- W4313016741 cites W3206858608 @default.
- W4313016741 cites W4220923746 @default.
- W4313016741 doi "https://doi.org/10.1109/iros47612.2022.9981759" @default.
- W4313016741 hasPublicationYear "2022" @default.
- W4313016741 type Work @default.
- W4313016741 citedByCount "4" @default.
- W4313016741 countsByYear W43130167412022 @default.
- W4313016741 countsByYear W43130167412023 @default.
- W4313016741 crossrefType "proceedings-article" @default.
- W4313016741 hasAuthorship W4313016741A5014874021 @default.
- W4313016741 hasBestOaLocation W43130167412 @default.
- W4313016741 hasConcept C105795698 @default.
- W4313016741 hasConcept C106189395 @default.
- W4313016741 hasConcept C112505250 @default.
- W4313016741 hasConcept C119857082 @default.
- W4313016741 hasConcept C127413603 @default.
- W4313016741 hasConcept C154945302 @default.
- W4313016741 hasConcept C159886148 @default.
- W4313016741 hasConcept C17744445 @default.
- W4313016741 hasConcept C185592680 @default.
- W4313016741 hasConcept C198531522 @default.
- W4313016741 hasConcept C199539241 @default.
- W4313016741 hasConcept C201995342 @default.
- W4313016741 hasConcept C25016198 @default.
- W4313016741 hasConcept C2775924081 @default.
- W4313016741 hasConcept C2776359362 @default.
- W4313016741 hasConcept C2776807809 @default.
- W4313016741 hasConcept C2780451532 @default.
- W4313016741 hasConcept C33923547 @default.
- W4313016741 hasConcept C41008148 @default.
- W4313016741 hasConcept C43617362 @default.
- W4313016741 hasConcept C4777664 @default.
- W4313016741 hasConcept C58581272 @default.
- W4313016741 hasConcept C80444323 @default.
- W4313016741 hasConcept C90509273 @default.
- W4313016741 hasConcept C94625758 @default.
- W4313016741 hasConcept C97541855 @default.
- W4313016741 hasConceptScore W4313016741C105795698 @default.
- W4313016741 hasConceptScore W4313016741C106189395 @default.
- W4313016741 hasConceptScore W4313016741C112505250 @default.
- W4313016741 hasConceptScore W4313016741C119857082 @default.
- W4313016741 hasConceptScore W4313016741C127413603 @default.
- W4313016741 hasConceptScore W4313016741C154945302 @default.
- W4313016741 hasConceptScore W4313016741C159886148 @default.
- W4313016741 hasConceptScore W4313016741C17744445 @default.
- W4313016741 hasConceptScore W4313016741C185592680 @default.
- W4313016741 hasConceptScore W4313016741C198531522 @default.
- W4313016741 hasConceptScore W4313016741C199539241 @default.
- W4313016741 hasConceptScore W4313016741C201995342 @default.
- W4313016741 hasConceptScore W4313016741C25016198 @default.
- W4313016741 hasConceptScore W4313016741C2775924081 @default.
- W4313016741 hasConceptScore W4313016741C2776359362 @default.
- W4313016741 hasConceptScore W4313016741C2776807809 @default.
- W4313016741 hasConceptScore W4313016741C2780451532 @default.
- W4313016741 hasConceptScore W4313016741C33923547 @default.
- W4313016741 hasConceptScore W4313016741C41008148 @default.
- W4313016741 hasConceptScore W4313016741C43617362 @default.
- W4313016741 hasConceptScore W4313016741C4777664 @default.
- W4313016741 hasConceptScore W4313016741C58581272 @default.
- W4313016741 hasConceptScore W4313016741C80444323 @default.
- W4313016741 hasConceptScore W4313016741C90509273 @default.
- W4313016741 hasConceptScore W4313016741C94625758 @default.
- W4313016741 hasConceptScore W4313016741C97541855 @default.
- W4313016741 hasLocation W43130167411 @default.
- W4313016741 hasLocation W43130167412 @default.
- W4313016741 hasOpenAccess W4313016741 @default.
- W4313016741 hasPrimaryLocation W43130167411 @default.
- W4313016741 hasRelatedWork W1545451257 @default.
- W4313016741 hasRelatedWork W2052111476 @default.
- W4313016741 hasRelatedWork W2061372038 @default.
- W4313016741 hasRelatedWork W2734058336 @default.
- W4313016741 hasRelatedWork W2951830773 @default.
- W4313016741 hasRelatedWork W2972520119 @default.
- W4313016741 hasRelatedWork W3090827750 @default.
- W4313016741 hasRelatedWork W4280567916 @default.
- W4313016741 hasRelatedWork W4286784054 @default.
- W4313016741 hasRelatedWork W4313016741 @default.
- W4313016741 isParatext "false" @default.